Papers › ConvMAE: Masked Convolution Meets Masked Autoencoders

ConvMAE: Masked Convolution Meets Masked Autoencoders

8 May 2022arXiv:2205.03892archive 2025-07-28

Peng Gao, Teli Ma, Hongsheng Li, Ziyi Lin, Jifeng Dai, Yu Qiao

Vision Transformers (ViT) become widely-adopted architectures for various vision tasks. Masked auto-encoding for feature pretraining and multi-scale hybrid convolution-transformer architectures can further unleash the potentials of ViT, leading to state-of-the-art performances on image classification, detection and semantic segmentation. In this paper, our ConvMAE framework demonstrates that multi-scale hybrid convolution-transformer can learn more discriminative representations via the mask auto-encoding scheme. However, directly using the original masking strategy leads to the heavy computational cost and pretraining-finetuning discrepancy. To tackle the issue, we adopt the masked convolution to prevent information leakage in the convolution blocks. A simple block-wise masking strategy is proposed to ensure computational efficiency. We also propose to more directly supervise the multi-scale features of the encoder to boost multi-scale features. Based on our pretrained ConvMAE models, ConvMAE-Base improves ImageNet-1K finetuning accuracy by 1.4% compared with MAE-Base. On object detection, ConvMAE-Base finetuned for only 25 epochs surpasses MAE-Base fined-tuned for 100 epochs by 2.9% box AP and 2.2% mask AP respectively. Code and pretrained models are available at https://github.com/Alpha-VL/ConvMAE.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2205.03892")

Code

Syntology Ran 5 of 10 code samples harvested from 2 repositories linked to this paper; 5 have no recorded run. Of those that ran: 5 ran with no contract checked.

By repository: official repository: 2 samples from 1 repository, 0 ran; community (archive-listed): 8 samples from 1 repository, 5 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

alpha-vl/convmae officialmentioned in papermentioned on GitHubpytorchMIT report
membrai/deblurringmim mentioned on GitHubpytorchNOASSERTION report
mx-mark/dmjd mentioned on GitHubpytorchMIT report
PaddlePaddle/PLSC paddleApache-2.0 report
pwc-1/Paper-9 mindspore report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

10 samples harvested; 5 ran; 0 honoured the contract we drafted; 5 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

5ran
5unverified

Licence: 0 of the 10 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

drop_path alpha-vl/convmae/DET/models/convmae.py official repository unverified MIT (permissive) · 52eff09408f9308d · report
resize_pos_embed alpha-vl/convmae/DET/models/convmae.py official repository unverified MIT (permissive) · 99a5f8dc62879d09 · report
build_dataset mx-mark/dmjd/util/datasets.py community (archive-listed) ran MIT (permissive) · 27f8c4c706fd43ec · report
build_transform mx-mark/dmjd/util/datasets.py community (archive-listed) ran MIT (permissive) · 800cebf161a8aa26 · report
has_file_allowed_extension mx-mark/dmjd/util/dataset_folder.py community (archive-listed) ran MIT (permissive) · 18ae3e6ef2cf02ec · report
is_image_file mx-mark/dmjd/util/dataset_folder.py community (archive-listed) ran MIT (permissive) · 8ac50ae8773b9431 · report
make_dataset mx-mark/dmjd/util/dataset_folder.py community (archive-listed) ran MIT (permissive) · fb6aea1653b20bba · report
expand_patches_indice mx-mark/dmjd/models_dmjd.py community (archive-listed) unverified MIT (permissive) · f4a4b75ad66dfa8d · report
hog_torch mx-mark/dmjd/util/hog_tensor.py community (archive-listed) unverified MIT (permissive) · aebb204ab2b5f5b3 · report
patchify mx-mark/dmjd/util/hog_tensor.py community (archive-listed) unverified MIT (permissive) · f66e302ee7963735 · report

Tasks

Computational EfficiencyImage ClassificationObject DetectionSemantic Segmentationimage-classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

ConvolutionMasked Convolution

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections